summaryrefslogtreecommitdiffstats
path: root/block
diff options
context:
space:
mode:
authorTejun Heo <tj@kernel.org>2009-05-07 22:24:41 +0900
committerJens Axboe <jens.axboe@oracle.com>2009-05-11 09:50:54 +0200
commit2e46e8b27aa57c6bd34b3102b40ee4d0144b4fab (patch)
tree134f560f66c2af277f0f25e5b85f6c1acaddfc06 /block
parent9780e2dd8254351f6cbe11304849126b51dbd561 (diff)
block: drop request->hard_* and *nr_sectors
struct request has had a few different ways to represent some properties of a request. ->hard_* represent block layer's view of the request progress (completion cursor) and the ones without the prefix are supposed to represent the issue cursor and allowed to be updated as necessary by the low level drivers. The thing is that as block layer supports partial completion, the two cursors really aren't necessary and only cause confusion. In addition, manual management of request detail from low level drivers is cumbersome and error-prone at the very least. Another interesting duplicate fields are rq->[hard_]nr_sectors and rq->{hard_cur|current}_nr_sectors against rq->data_len and rq->bio->bi_size. This is more convoluted than the hard_ case. rq->[hard_]nr_sectors are initialized for requests with bio but blk_rq_bytes() uses it only for !pc requests. rq->data_len is initialized for all request but blk_rq_bytes() uses it only for pc requests. This causes good amount of confusion throughout block layer and its drivers and determining the request length has been a bit of black magic which may or may not work depending on circumstances and what the specific LLD is actually doing. rq->{hard_cur|current}_nr_sectors represent the number of sectors in the contiguous data area at the front. This is mainly used by drivers which transfers data by walking request segment-by-segment. This value always equals rq->bio->bi_size >> 9. However, data length for pc requests may not be multiple of 512 bytes and using this field becomes a bit confusing. In general, having multiple fields to represent the same property leads only to confusion and subtle bugs. With recent block low level driver cleanups, no driver is accessing or manipulating these duplicate fields directly. Drop all the duplicates. Now rq->sector means the current sector, rq->data_len the current total length and rq->bio->bi_size the current segment length. Everything else is defined in terms of these three and available only through accessors. * blk_recalc_rq_sectors() is collapsed into blk_update_request() and now handles pc and fs requests equally other than rq->sector update. This means that now pc requests can use partial completion too (no in-kernel user yet tho). * bio_cur_sectors() is replaced with bio_cur_bytes() as block layer now uses byte count as the primary data length. * blk_rq_pos() is now guranteed to be always correct. In-block users converted. * blk_rq_bytes() is now guaranteed to be always valid as is blk_rq_sectors(). In-block users converted. * blk_rq_sectors() is now guaranteed to equal blk_rq_bytes() >> 9. More convenient one is used. * blk_rq_bytes() and blk_rq_cur_bytes() are now inlined and take const pointer to request. [ Impact: API cleanup, single way to represent one property of a request ] Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Boaz Harrosh <bharrosh@panasas.com> Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Diffstat (limited to 'block')
-rw-r--r--block/blk-core.c81
-rw-r--r--block/blk-merge.c36
-rw-r--r--block/blk.h1
-rw-r--r--block/cfq-iosched.c10
4 files changed, 39 insertions, 89 deletions
diff --git a/block/blk-core.c b/block/blk-core.c
index 82dc20621c0..3596ca71909 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -127,7 +127,7 @@ void blk_rq_init(struct request_queue *q, struct request *rq)
INIT_LIST_HEAD(&rq->timeout_list);
rq->cpu = -1;
rq->q = q;
- rq->sector = rq->hard_sector = (sector_t) -1;
+ rq->sector = (sector_t) -1;
INIT_HLIST_NODE(&rq->hash);
RB_CLEAR_NODE(&rq->rb_node);
rq->cmd = rq->__cmd;
@@ -189,8 +189,7 @@ void blk_dump_rq_flags(struct request *rq, char *msg)
(unsigned long long)blk_rq_pos(rq),
blk_rq_sectors(rq), blk_rq_cur_sectors(rq));
printk(KERN_INFO " bio %p, biotail %p, buffer %p, len %u\n",
- rq->bio, rq->biotail,
- rq->buffer, rq->data_len);
+ rq->bio, rq->biotail, rq->buffer, blk_rq_bytes(rq));
if (blk_pc_request(rq)) {
printk(KERN_INFO " cdb: ");
@@ -1096,7 +1095,7 @@ void init_request_from_bio(struct request *req, struct bio *bio)
req->cmd_flags |= REQ_NOIDLE;
req->errors = 0;
- req->hard_sector = req->sector = bio->bi_sector;
+ req->sector = bio->bi_sector;
req->ioprio = bio_prio(bio);
blk_rq_bio_prep(req->q, req, bio);
}
@@ -1113,14 +1112,13 @@ static inline bool queue_should_plug(struct request_queue *q)
static int __make_request(struct request_queue *q, struct bio *bio)
{
struct request *req;
- int el_ret, nr_sectors;
+ int el_ret;
+ unsigned int bytes = bio->bi_size;
const unsigned short prio = bio_prio(bio);
const int sync = bio_sync(bio);
const int unplug = bio_unplug(bio);
int rw_flags;
- nr_sectors = bio_sectors(bio);
-
/*
* low level driver can indicate that it wants pages above a
* certain limit bounced to low memory (ie for highmem, or even
@@ -1145,7 +1143,7 @@ static int __make_request(struct request_queue *q, struct bio *bio)
req->biotail->bi_next = bio;
req->biotail = bio;
- req->nr_sectors = req->hard_nr_sectors += nr_sectors;
+ req->data_len += bytes;
req->ioprio = ioprio_best(req->ioprio, prio);
if (!blk_rq_cpu_valid(req))
req->cpu = bio->bi_comp_cpu;
@@ -1171,10 +1169,8 @@ static int __make_request(struct request_queue *q, struct bio *bio)
* not touch req->buffer either...
*/
req->buffer = bio_data(bio);
- req->current_nr_sectors = bio_cur_sectors(bio);
- req->hard_cur_sectors = req->current_nr_sectors;
- req->sector = req->hard_sector = bio->bi_sector;
- req->nr_sectors = req->hard_nr_sectors += nr_sectors;
+ req->sector = bio->bi_sector;
+ req->data_len += bytes;
req->ioprio = ioprio_best(req->ioprio, prio);
if (!blk_rq_cpu_valid(req))
req->cpu = bio->bi_comp_cpu;
@@ -1557,7 +1553,7 @@ EXPORT_SYMBOL(submit_bio);
int blk_rq_check_limits(struct request_queue *q, struct request *rq)
{
if (blk_rq_sectors(rq) > q->max_sectors ||
- rq->data_len > q->max_hw_sectors << 9) {
+ blk_rq_bytes(rq) > q->max_hw_sectors << 9) {
printk(KERN_ERR "%s: over max size limit.\n", __func__);
return -EIO;
}
@@ -1675,35 +1671,6 @@ static void blk_account_io_done(struct request *req)
}
}
-/**
- * blk_rq_bytes - Returns bytes left to complete in the entire request
- * @rq: the request being processed
- **/
-unsigned int blk_rq_bytes(struct request *rq)
-{
- if (blk_fs_request(rq))
- return blk_rq_sectors(rq) << 9;
-
- return rq->data_len;
-}
-EXPORT_SYMBOL_GPL(blk_rq_bytes);
-
-/**
- * blk_rq_cur_bytes - Returns bytes left to complete in the current segment
- * @rq: the request being processed
- **/
-unsigned int blk_rq_cur_bytes(struct request *rq)
-{
- if (blk_fs_request(rq))
- return rq->current_nr_sectors << 9;
-
- if (rq->bio)
- return rq->bio->bi_size;
-
- return rq->data_len;
-}
-EXPORT_SYMBOL_GPL(blk_rq_cur_bytes);
-
struct request *elv_next_request(struct request_queue *q)
{
struct request *rq;
@@ -1736,7 +1703,7 @@ struct request *elv_next_request(struct request_queue *q)
if (rq->cmd_flags & REQ_DONTPREP)
break;
- if (q->dma_drain_size && rq->data_len) {
+ if (q->dma_drain_size && blk_rq_bytes(rq)) {
/*
* make sure space for the drain appears we
* know we can do this because max_hw_segments
@@ -1759,7 +1726,7 @@ struct request *elv_next_request(struct request_queue *q)
* avoid resource deadlock. REQ_STARTED will
* prevent other fs requests from passing this one.
*/
- if (q->dma_drain_size && rq->data_len &&
+ if (q->dma_drain_size && blk_rq_bytes(rq) &&
!(rq->cmd_flags & REQ_DONTPREP)) {
/*
* remove the space for the drain we added
@@ -1911,8 +1878,7 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
* can find how many bytes remain in the request
* later.
*/
- req->nr_sectors = req->hard_nr_sectors = 0;
- req->current_nr_sectors = req->hard_cur_sectors = 0;
+ req->data_len = 0;
return false;
}
@@ -1926,8 +1892,25 @@ bool blk_update_request(struct request *req, int error, unsigned int nr_bytes)
bio_iovec(bio)->bv_len -= nr_bytes;
}
- blk_recalc_rq_sectors(req, total_bytes >> 9);
+ req->data_len -= total_bytes;
+ req->buffer = bio_data(req->bio);
+
+ /* update sector only for requests with clear definition of sector */
+ if (blk_fs_request(req) || blk_discard_rq(req))
+ req->sector += total_bytes >> 9;
+
+ /*
+ * If total number of sectors is less than the first segment
+ * size, something has gone terribly wrong.
+ */
+ if (blk_rq_bytes(req) < blk_rq_cur_bytes(req)) {
+ printk(KERN_ERR "blk: request botched\n");
+ req->data_len = blk_rq_cur_bytes(req);
+ }
+
+ /* recalculate the number of segments */
blk_recalc_rq_segments(req);
+
return true;
}
EXPORT_SYMBOL_GPL(blk_update_request);
@@ -2049,11 +2032,7 @@ void blk_rq_bio_prep(struct request_queue *q, struct request *rq,
rq->nr_phys_segments = bio_phys_segments(q, bio);
rq->buffer = bio_data(bio);
}
- rq->current_nr_sectors = bio_cur_sectors(bio);
- rq->hard_cur_sectors = rq->current_nr_sectors;
- rq->hard_nr_sectors = rq->nr_sectors = bio_sectors(bio);
rq->data_len = bio->bi_size;
-
rq->bio = rq->biotail = bio;
if (bio->bi_bdev)
diff --git a/block/blk-merge.c b/block/blk-merge.c
index bf62a87a9da..b8df66aef0f 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -9,35 +9,6 @@
#include "blk.h"
-void blk_recalc_rq_sectors(struct request *rq, int nsect)
-{
- if (blk_fs_request(rq) || blk_discard_rq(rq)) {
- rq->hard_sector += nsect;
- rq->hard_nr_sectors -= nsect;
-
- /*
- * Move the I/O submission pointers ahead if required.
- */
- if ((rq->nr_sectors >= rq->hard_nr_sectors) &&
- (rq->sector <= rq->hard_sector)) {
- rq->sector = rq->hard_sector;
- rq->nr_sectors = rq->hard_nr_sectors;
- rq->hard_cur_sectors = bio_cur_sectors(rq->bio);
- rq->current_nr_sectors = rq->hard_cur_sectors;
- rq->buffer = bio_data(rq->bio);
- }
-
- /*
- * if total number of sectors is less than the first segment
- * size, something has gone terribly wrong
- */
- if (rq->nr_sectors < rq->current_nr_sectors) {
- printk(KERN_ERR "blk: request botched\n");
- rq->nr_sectors = rq->current_nr_sectors;
- }
- }
-}
-
static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
struct bio *bio)
{
@@ -199,8 +170,9 @@ new_segment:
if (unlikely(rq->cmd_flags & REQ_COPY_USER) &&
- (rq->data_len & q->dma_pad_mask)) {
- unsigned int pad_len = (q->dma_pad_mask & ~rq->data_len) + 1;
+ (blk_rq_bytes(rq) & q->dma_pad_mask)) {
+ unsigned int pad_len =
+ (q->dma_pad_mask & ~blk_rq_bytes(rq)) + 1;
sg->length += pad_len;
rq->extra_len += pad_len;
@@ -398,7 +370,7 @@ static int attempt_merge(struct request_queue *q, struct request *req,
req->biotail->bi_next = next->bio;
req->biotail = next->biotail;
- req->nr_sectors = req->hard_nr_sectors += next->hard_nr_sectors;
+ req->data_len += blk_rq_bytes(next);
elv_merge_requests(q, req, next);
diff --git a/block/blk.h b/block/blk.h
index 51115599df9..ab54529103c 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -101,7 +101,6 @@ int ll_front_merge_fn(struct request_queue *q, struct request *req,
int attempt_back_merge(struct request_queue *q, struct request *rq);
int attempt_front_merge(struct request_queue *q, struct request *rq);
void blk_recalc_rq_segments(struct request *rq);
-void blk_recalc_rq_sectors(struct request *rq, int nsect);
void blk_queue_congestion_threshold(struct request_queue *q);
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index db4d990a66b..99ac4304d71 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -579,9 +579,9 @@ cfq_prio_tree_lookup(struct cfq_data *cfqd, struct rb_root *root,
* Sort strictly based on sector. Smallest to the left,
* largest to the right.
*/
- if (sector > cfqq->next_rq->sector)
+ if (sector > blk_rq_pos(cfqq->next_rq))
n = &(*p)->rb_right;
- else if (sector < cfqq->next_rq->sector)
+ else if (sector < blk_rq_pos(cfqq->next_rq))
n = &(*p)->rb_left;
else
break;
@@ -611,8 +611,8 @@ static void cfq_prio_tree_add(struct cfq_data *cfqd, struct cfq_queue *cfqq)
return;
cfqq->p_root = &cfqd->prio_trees[cfqq->org_ioprio];
- __cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root, cfqq->next_rq->sector,
- &parent, &p);
+ __cfqq = cfq_prio_tree_lookup(cfqd, cfqq->p_root,
+ blk_rq_pos(cfqq->next_rq), &parent, &p);
if (!__cfqq) {
rb_link_node(&cfqq->p_node, parent, p);
rb_insert_color(&cfqq->p_node, cfqq->p_root);
@@ -996,7 +996,7 @@ static struct cfq_queue *cfqq_close(struct cfq_data *cfqd,
if (cfq_rq_close(cfqd, __cfqq->next_rq))
return __cfqq;
- if (__cfqq->next_rq->sector < sector)
+ if (blk_rq_pos(__cfqq->next_rq) < sector)
node = rb_next(&__cfqq->p_node);
else
node = rb_prev(&__cfqq->p_node);